DeepSeek V4 Flash
prime/deepseek/deepseek-v4-flash · family deepseek-flash · in: text → out: text · price provider-declared (via models.dev). Capabilities: tools reasoning text.
$0.66
Blended $/1M (3:1)
$0.44
Input $/1M
$1.32
Output $/1M
$1.76
1M in + 1M out
—
Cache read $/1M
#3507 of 8,071
Cheapest rank
- Provider
- Prime Inference (
prime) - Kind
- text (outputs text)
- Context
- 1,048,576 tokens
- Max output
- 943,718 tokens
- Capabilities
- tools reasoning text
Same model, other providers
“DeepSeek V4 Flash” is offered by 53 providers — cheapest-effective first. SenseNova (China) is the cheapest at $0.00 blended.
| Provider | Input | Output | Blended | Context |
|---|---|---|---|---|
| SenseNova (China) | free | free | $0.00 | 1M |
| Alibaba Token Plan | free | free | $0.00 | 1M |
| Umans AI Coding Plan | free | free | $0.00 | 1M |
| Alibaba Token Plan (China) | free | free | $0.00 | 1M |
| Pendra | free | free | $0.00 | 1M |
| UnoRouter | free | free | $0.00 | 1M |
| Volcengine Ark Coding Plan | free | free | $0.00 | 1M |
| SCNet Token Plan | free | free | $0.00 | 1M |
| Kenari | free | free | $0.00 | 1M |
| Merge Gateway | $0.035 | $0.07 | $0.04 | 1M |
| DevPass (LLM Gateway) | $0.065 | $0.116 | $0.08 | 1.1M |
| Deep Infra | $0.09 | $0.18 | $0.11 | 1M |
| Prime Inference (this) | $0.44 | $1.32 | $0.66 | 1M |
Call it
jishie indexes & prices models; it does not proxy inference.
Most providers are OpenAI-compatible — point base_url at Prime Inference and pass this model id:
curl $BASE_URL/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
-d '{"model":"deepseek/deepseek-v4-flash","messages":[{"role":"user","content":"hello"}]}'
Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):